Skip to content

Latest commit

 

History

History
12 lines (9 loc) · 392 Bytes

README.md

File metadata and controls

12 lines (9 loc) · 392 Bytes

Reinforcement Learning

some practices to keep records...

Q Learning

  • Rooms practice
    Goal: Given a grid world with 6 rooms, find an optimized path to reach goal!

DQN (using TF-Agents)

  • Cartpole practice
    Goal: Given a cartpole, try to keep the pole upright by moving the cartpole left or right!

PPO